NVIDIA GeForce RTX 4070 AD103 vs NVIDIA GeForce GT 645 OEM
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 AD103 and 1024MB VRAM GeForce GT 645 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 AD103 's Advantages
Released 11 years and 11 months late
Boost Clock2475MHz
More VRAM (12GB vs 1024GB)
Larger VRAM bandwidth (504.2GB/s vs 91.87GB/s)
5600 additional rendering cores
NVIDIA GeForce GT 645 OEM 's Advantages
Lower TDP (102W vs 200W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 AD103
+3160%
29.15 TFLOPS
GeForce GT 645 OEM
0.894 TFLOPS
Graphics Card
Mar 2024
Release Date
Apr 2012
GeForce 40
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1920 MHz
Base Clock
-
2475 MHz
Boost Clock
-
1313 MHz
Memory Clock
957 MHz
Memory
12GB
Memory Size
1024MB
GDDR6X
Memory Type
GDDR5
192bit
Memory Bus
192bit
504.2GB/s
Bandwidth
91.87GB/s
Render Config
-
-
-
46
SM Count
6
5888
Shading Units
288
184
TMUs
48
64
ROPs
24
184
Tensor Cores
-
46
RT Cores
-
128 KB (per SM)
L1 Cache
64 KB (per SM)
36 MB
L2 Cache
384 KB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
9.312 GPixel/s
455.4 GTexel/s
Texture Rate
37.25 GTexel/s
29.15 TFLOPS
FP16 (half)
-
29.15 TFLOPS
FP32 (float)
894.0 GFLOPS
455.4 GFLOPS
FP64 (double)
74.50 GFLOPS
Board Design
200W
TDP
102W
550 W
Suggested PSU
300 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
2x DVI
1x mini-HDMI 1.3a
1x 16-pin
Power Connectors
-
Graphics Processor
AD103
GPU Name
GF114
AD103-175-K1-A1
GPU Variant
-
Ada Lovelace
Architecture
Fermi 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
40 nm
45.9 billion
Transistors
1.95 billion
379 mm²
Die Size
332 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
1.1
1.3
Vulkan
N/A
8.9
CUDA
2.1
6.7
Shader Model
5.1
